Year: 2024
Type: article
Abstract: Crop disease detection is pivotal for ensuring food security and sustainable agriculture. Traditional methods often struggle to accurately identify diseased plants, resulting in substantial yield losses. In agricultural contexts, detection of disease is very important so that we get maximum yield and ensures the crop quality or crop health. As we know that for any work related to images we often use CNN convolutional neural network as it work really great due to its architecture thus its use is often seen in leaf disease detection and mostly this traditional approaches use raw leaf image and feed it to CNN to train which may not work if the dataset is very low or we may not get satisfactory accuracy this is because it is not able to capture that pattern, and also in some scenarios diseases spots manifest as light or closely resemble the background coluor of the leaf thus it requires more data to discern such a subtle patterns.
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: hybrid
OpenAlex ID: W4402477068